D2-Net: A Trainable CNN for Joint Description and Detectionof Local Features
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F19%3A00336316" target="_blank" >RIV/68407700:21730/19:00336316 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21730/19:00337394
Result on the web
<a href="https://doi.org/10.1109/CVPR.2019.00828" target="_blank" >https://doi.org/10.1109/CVPR.2019.00828</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/CVPR.2019.00828" target="_blank" >10.1109/CVPR.2019.00828</a>
Alternative languages
Result language
angličtina
Original language name
D2-Net: A Trainable CNN for Joint Description and Detectionof Local Features
Original language description
In this work, we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector.By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counter-parts based on early detection of low-level structures. Weshow that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Night localization dataset and theInLoc indoor localization benchmark, as well as competitive performance on other benchmarks for image matching and 3D reconstruction.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
CVPR 2019: Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition
ISBN
978-1-7281-3294-5
ISSN
1063-6919
e-ISSN
2575-7075
Number of pages
10
Pages from-to
8084-8093
Publisher name
IEEE
Place of publication
—
Event location
Long Beach
Event date
Jun 15, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—